Scholar
Yi-Ling Chung
Google Scholar ID: 276kTuoAAAAJ
Multiverse Computing
Citations & Impact
Citations
699
H-index
10
i10-index
11
Publications
20
Co-authors
2
list available
Publications
Resume (English only)
Academic Achievements
- March 2025: Co-organizing a tutorial on NLP for Counterspeech against Hate and Misinformation at ACL 2025
- May 2024: Two papers accepted at NAACL 2024; co-organizing the 8th Workshop on Online Abuse and Harms (WOAH 2024)
- 2023: Delivered talks and participated in panels on online harm mitigation and disinformation in generative AI at University of Jaén, Ofcom, AI UK, and the Symposium on AI, Free Speech and Human Rights
- November 2022: Gave a talk on automatic hate countering at Heriot-Watt University
- 2021: Multiple papers accepted at ArgMining 2021, ACL Findings, NLP4PI, and the journal Online Social Networks and Media
- Successfully defended PhD thesis in April 2021
- Key publications include: 'Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking' (2025), 'On the Effectiveness of Adversarial Robustness for Abuse Mitigation with Counterspeech' (NAACL 2024), and 'NLP for Counterspeech against Hate: A Survey and How-To Guide' (NAACL Findings 2024)
Background
- Senior Data Scientist at Multiverse Computing
- Focuses on benchmarking AI models through evaluation, dataset creation, and post-training
- Passionate about developing real-world applications addressing societal issues such as health, misinformation, abuse, and violence
- Interested in the social impact of AI systems and making AI safer and more reliable
- Research interests include model evaluation, multilinguality, generalizable NLP, LLM hallucination mitigation, argument mining and generation, and psychology
